--- title: Anthropic speeds up Claude Code with message threads.... description: Anthropic's message threads feature cuts latency in long-running Claude Code sessions by letting the API retain conversation history server-side instead of... canonical: https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Anthropic speeds up Claude Code with message threads. But your token bill stays the same. | daily.dev og:description: Anthropic's message threads feature cuts latency in long-running Claude Code sessions by letting the API retain conversation history server-side instead of... og:url: https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n og:image: https://api.daily.dev/og/posts/IrCD5zd2n.png og:image:alt: Anthropic speeds up Claude Code with message threads. But your token bill stays the same. og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Anthropic speeds up Claude Code with message threads. But your token bill stays the same. **[The New Stack](https://daily.dev/sources/newstack)** · 18 min read · 0 upvotes · 0 comments ## Summary Anthropic's message threads feature cuts latency in long-running Claude Code sessions by letting the API retain conversation history server-side instead of resending it every request. It has reduced median time to first token by about 35% for Claude Code requests between 500,000 and 1 million tokens. Claude still processes the full conversation on every turn, so token usage and cost stay the same; only the data transmitted shrinks. Threads expire after 5 minutes of inactivity, though active sessions refresh the timer and SDK helpers can auto-resend history after a lapse. It's in beta across the Messages API, including AWS, Microsoft Foundry and Google Cloud. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Does Claude Code's new message threads feature reduce my token usage and API costs? No, token usage stays the same because Claude still reads the full conversation history on every turn even though each request transmits less data. Message threads only reduces the data sent over the network, cutting median time to first token by about 35% for requests between 500,000 and 1 million tokens. To cut actual costs, combine it with Claude's prompt caching feature, which charges discounted rates for reused content. _Track how new Claude API features actually affect latency versus cost on daily.dev before you adopt them._ ### How long before a Claude Code message thread expires if I stop sending requests? A message thread expires after five minutes of inactivity. If a developer steps away and the thread expires, the SDK helper automatically resends the retained conversation history to establish a new thread on the next request, so the session continues without losing context, though that first request after the break may take longer. Every successful request also refreshes the five-minute expiry window. _Developers tuning long Claude Code sessions can follow these API behavior details on daily.dev._ ### How do I enable message threads in the Claude Messages API using the Python SDK? Create a client with anthropic.Anthropic(), then initialize a thread via client.beta.messages.thread(), passing the model, max output tokens, and system prompt. Call thread.send() to submit messages; the SDK automatically creates the thread on the first call and continues it afterward, retaining a local copy of history. Direct API users must include the anthropic-beta header with value message-threads-2026-08-12. _Developers wiring up new beta APIs can keep headers and SDK changes straight via daily.dev._ ## Similar posts on daily.dev - [Claude Code cache confusion as Anthropic tweaks defaults, but quotas still drain](https://daily.dev/posts/claude-code-cache-confusion-as-anthropic-tweaks-defaults-but-quotas-still-drain-uvn7zes3k) · DEVCLASS · 5 upvotes · 1 comments - [Anthropic quietly nerfed Claude Code's 1-hour cache, and your token budget is paying the price](https://daily.dev/posts/anthropic-quietly-nerfed-claude-code-s-1-hour-cache-and-your-token-budget-is-paying-the-price-1jobhvzkb) · XDA Developers · 1 upvotes · 0 comments - [Claude devs complain about surprise usage limits](https://daily.dev/posts/claude-devs-complain-about-surprise-usage-limits-tbjb8dqml) · The Register · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#anthropic](https://daily.dev/tags/anthropic), [#claude-code](https://daily.dev/tags/claude-code), [#ai-inference](https://daily.dev/tags/ai-inference) [View this post on daily.dev](https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Anthropic speeds up Claude Code with message threads. But your token bill stays the same.","url":"https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n"},"datePublished":"2026-11-03T13:48:19.094Z","dateModified":"2026-11-04T08:00:36.818Z","description":"Anthropic's message threads feature cuts latency in long-running Claude Code sessions by letting the API retain conversation history server-side instead of...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d0e16919e3c4b1065b2aff8771d3cb43?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d0e16919e3c4b1065b2aff8771d3cb43?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"The New Stack","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"The New Stack","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/newstack","url":"https://daily.dev/sources/newstack"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,anthropic,claude-code,ai-inference","timeRequired":"PT18M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"The New Stack","item":"https://daily.dev/sources/newstack"},{"@type":"ListItem","position":3,"name":"Anthropic speeds up Claude Code with message threads. But your token bill stays the same."}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/anthropic-speeds-up-claude-code-with-message-threads-but-your-token-bill-stays-the-same--ircd5zd2n#faq","mainEntity":[{"@type":"Question","name":"Does Claude Code's new message threads feature reduce my token usage and API costs?","acceptedAnswer":{"@type":"Answer","text":"No, token usage stays the same because Claude still reads the full conversation history on every turn even though each request transmits less data. Message threads only reduces the data sent over the network, cutting median time to first token by about 35% for requests between 500,000 and 1 million tokens. To cut actual costs, combine it with Claude's prompt caching feature, which charges discounted rates for reused content. Track how new Claude API features actually affect latency versus cost on daily.dev before you adopt them."}},{"@type":"Question","name":"How long before a Claude Code message thread expires if I stop sending requests?","acceptedAnswer":{"@type":"Answer","text":"A message thread expires after five minutes of inactivity. If a developer steps away and the thread expires, the SDK helper automatically resends the retained conversation history to establish a new thread on the next request, so the session continues without losing context, though that first request after the break may take longer. Every successful request also refreshes the five-minute expiry window. Developers tuning long Claude Code sessions can follow these API behavior details on daily.dev."}},{"@type":"Question","name":"How do I enable message threads in the Claude Messages API using the Python SDK?","acceptedAnswer":{"@type":"Answer","text":"Create a client with anthropic.Anthropic(), then initialize a thread via client.beta.messages.thread(), passing the model, max output tokens, and system prompt. Call thread.send() to submit messages; the SDK automatically creates the thread on the first call and continues it afterward, retaining a local copy of history. Direct API users must include the anthropic-beta header with value message-threads-2026-08-12. Developers wiring up new beta APIs can keep headers and SDK changes straight via daily.dev."}}]} ```